2

我正在尝试使用 OVERFLOW-PLOT3D q-file 格式(在此处定义:http://overflow.larc.nasa.gov/files/2014/06/Appendix_A.pdf)保存解决方案。对于单个网格,基本上是,

READ(1) NGRID
READ(1) JD,KD,LD,NQ,NQC
READ(1) REFMACH,ALPHA,REY,TIME,GAMINF,BETA,TINF, &
        IGAM,HTINF,HT1,HT2,RGAS1,RGAS2, &
        FSMACH,TVREF,DTVREF
READ(1) ((((Q(J,K,L,N),J=1,JD),K=1,KD),L=1,LD),N=1,NQ)    

所有变量都是双精度数,除了 NGRID、JD、KD、LD、NQ、NQC 和 IGAM 是整数。我需要使用 MPI-IO 来导出解决方案。如果我举一个非常简单的单处理器示例,下面的代码不起作用,但我不明白为什么。

call mpi_file_open( mpi_comm_world, fileOut, mpi_mode_wronly + mpi_mode_create, &
                  mpi_info_null, mpi_fh, ierr )
offset = 0
call mpi_file_seek( mpi_fh, offset, mpi_seek_set, ierr )
call mpi_file_write( mpi_fh, (/NGRID,JD,KD,LD,NQ,NQC/), 6, mpi_integer, mstat, ierr )
call mpi_file_write( mpi_fh, (/REFMACH,ALPHA,REY,TIME,GAMINF,BETA,TINF/), 7, mpi_double_precision, mstat, ierr )
call mpi_file_write( mpi_fh, IGAM, 1, mpi_integer, mstat, ierr )
call mpi_file_write( mpi_fh, (/HTINF,HT1,HT2,RGAS1,RGAS2,FSMACH,TVREF,DTVREF/), 8, mpi_double_precision, mstat, ierr )

call mpi_file_write( mpi_fh, Q, NQ*JD*KD*LD, mpi_double_precision, mstat, ierr )

Tecplot 无法识别该格式。但是,如果我编写一个简单的非 MPI 代码,例如这个:

open(2, file=fileOut, form='unformatted', convert='little_endian')
write(2) NGRID
write(2) JD, KD, LD, NQ, NQC
write(2) REFMACH,ALPHA,REY,TIME,GAMINF,BETA,TINF, &
         IGAM,HTINF,HT1,HT2,RGAS1,RGAS2, &
         FSMACH,TVREF,DTVREF
write(2) ((((Q(J,K,L,N),J=1,JD),K=1,KD),L=1,LD),N=1,NQ)

一切正常。我的 MPI-IO 代码有什么问题?非常感谢您的帮助!

约阿希姆

注意:我不知道这是否相关,但如果我在最后的写入语句之前添加一个 mpi_file_seek(offset),偏移量 = 144。Tecplot 同意加载文件(但数据未正确读取)。这很奇怪,因为正常的偏移量应该是 7 个整数 + 15 个实数 *8 = 148 个字节...

编辑:由于某种原因,您的方法@Jonathan Dursi 似乎不适用于 Tecplot。下面的代码有什么问题吗?(简化为单个处理器)

 call MPI_File_write(fileh, [4, ngrid, 4], 3, MPI_INTEGER, MPI_STATUS_IGNORE, ierr)
 call MPI_File_write(fileh, [20, jd, kd, ld, nq, nqc, 20], 7, MPI_INTEGER, MPI_STATUS_IGNORE, ierr)
 call MPI_File_write(fileh, [56], 1, MPI_INTEGER, MPI_STATUS_IGNORE, ierr)
 call MPI_File_write(fileh, [refmach,alpha,rey,time,gaminf,beta,tinf], 7, MPI_double_precision, MPI_STATUS_IGNORE, ierr)
 call MPI_File_write(fileh, [56], 1, MPI_INTEGER, MPI_STATUS_IGNORE, ierr)
 call MPI_File_write(fileh, [4, IGAM, 4], 3, MPI_INTEGER, MPI_STATUS_IGNORE, ierr)
 call MPI_File_write(fileh, [64], 1, MPI_INTEGER, MPI_STATUS_IGNORE, ierr)
 call MPI_File_write(fileh, [HTINF,HT1,HT2,RGAS1,RGAS2,FSMACH,TVREF,DTVREF], 8, MPI_double_precision, MPI_STATUS_IGNORE, ierr)
 call MPI_File_write(fileh, [64], 1, MPI_INTEGER, MPI_STATUS_IGNORE, ierr)
 call MPI_File_write(fileh, [jd*kd*ld*nq*8], 1, MPI_INTEGER, MPI_STATUS_IGNORE, ierr)
 call MPI_File_write(fileh, q, jd*kd*ld*nq, MPI_double_precision, MPI_STATUS_IGNORE, ierr)
 call MPI_File_write(fileh, [jd*kd*ld*nq*8], 1, MPI_INTEGER, MPI_STATUS_IGNORE, ierr)
4

1 回答 1

6

@francescalus 是对的——Fortran顺序无格式数据是基于记录的——这实际上对很多事情都非常好,但没有其他东西使用它(甚至 Fortran 中的 MPI-IO,它更像 C——文件只是很长未区分字节流)。

让我们看一下问题中您编写程序的简化版本:

program testwrite

integer, parameter:: ngrid=2
integer, parameter:: jd=4, kd=3, ld=2, nq=1, nqc=-1

integer, parameter :: refmach=1, alpha=2, rey=3, time=4, gaminf=5
integer, parameter :: beta=6, tinf=7

integer, dimension(jd,kd,ld,nq) :: q
q = 0

open(2, file='ftest.dat', form='unformatted', convert='little_endian')
write(2) NGRID
write(2) JD, KD, LD, NQ, NQC
write(2) REFMACH,ALPHA,REY,TIME,GAMINF,BETA,TINF
write(2) ((((Q(J,K,L,N),J=1,JD),K=1,KD),L=1,LD),N=1,NQ)
close(2)

end program testwrite

运行它,并查看生成的二进制文件od(为了清楚地查看二进制文件,我将所有内容都设为整数):

$ gfortran -o fwrite fwrite.f90 
$ ./fwrite 
$ od --format "d" ftest.dat 
0000000           4           2           4          20
0000020           4           3           2           1
0000040          -1          20          28           1
0000060           2           3           4           5
0000100           6           7          28          96
0000120           0           0           0           0
*
0000260          96
0000264

例如,我们在开头看到 ngrid (2) 整数,以 4/4 结尾——记录的大小(以字节为单位)。然后,以 20/20 结尾,我们看到 5 个整数(5*4 字节)4、3、2、1、-1 -- jd、kd、ld、nq、nqc。最后,我们看到一堆以 96 (= 4bytes/integer *4*3*2*1) 结尾的零,代表 q。(请注意,没有定义此行为的标准,但我不知道任何主要的 Fortran 编译器不这样做;但是,当记录变得大于 4 字节整数可以描述时,行为开始不同。

我们可以使用下面的简单程序来测试数据文件:

program testread

implicit none

integer :: ngrid
integer :: jd, kd, ld, nq, nqc

integer :: refmach, alpha, rey, time, gaminf
integer :: beta, tinf

integer :: j, k, l, n

integer, allocatable, dimension(:,:,:,:) :: q
character(len=64) :: filename

if (command_argument_count() < 1) then
    print *,'Usage: read [filename]'
else 
    call get_command_argument(1, filename)
    open(2, file=trim(filename), form='unformatted', convert='little_endian')
    read(2) NGRID
    read(2) JD, KD, LD, NQ, NQC
    read(2) REFMACH,ALPHA,REY,TIME,GAMINF,BETA,TINF

    allocate(q(jd, kd, ld, nq))
    read(2) ((((Q(J,K,L,N),J=1,JD),K=1,KD),L=1,LD),N=1,NQ)
    close(2)

    print *, 'Ngrid = ', ngrid
    print *, 'jd, kd, ld, nq, nqc = ', jd, kd, ld, nq, nqc

    print *, 'q: min/mean/max = ', minval(q), sum(q)/size(q), maxval(q)
    deallocate(q)
endif

end program testread

和跑步给

$ ./fread ftest.dat 
 Ngrid =            2
 jd, kd, ld, nq, nqc =            4           3           2           1          -1
 q: min/mean/max =            0           0           0

很简单。

所以这种行为在 MPI-IO 中很容易模仿。这里实际上有三个部分——标题 Q,我假设它是分布式的(例如,MPI 子数组)和页脚(它只是数组的书挡)。

因此,让我们看一下 Fortran 中的一个 MPI-IO 程序,它会做同样的事情:

program mpiwrite

  use mpi
  implicit none

  integer, parameter:: ngrid=2
  integer, parameter:: jd=3, kd=3, ld=3, nlocq=3, nqc=-1
  integer :: nq

  integer, parameter :: refmach=1, alpha=2, rey=3, time=4, gaminf=5
  integer, parameter :: beta=6, tinf=7

  integer, dimension(jd,kd,ld,nlocq) :: q

  integer :: intsize
  integer :: subarray

  integer :: fileh
  integer(kind=MPI_Offset_kind) :: offset

  integer :: comsize, rank, ierr

  call MPI_Init(ierr)
  call MPI_Comm_size(MPI_COMM_WORLD, comsize, ierr)
  call MPI_Comm_rank(MPI_COMM_WORLD, rank, ierr)

  nq = nlocq * comsize
  q = rank

  ! create a subarray; each processor gets its own q-slice of the
  ! global array
  call MPI_Type_create_subarray (4, [jd, kd, ld, nq], [jd, kd, ld, nlocq], &
                                    [0, 0, 0, nlocq*rank], &
                                    MPI_ORDER_FORTRAN, MPI_INTEGER, subarray,  ierr)
  call MPI_Type_commit(subarray, ierr)

  call MPI_File_open(MPI_COMM_WORLD, 'mpi.dat',         &
                     MPI_MODE_WRONLY + MPI_MODE_CREATE, &
                     MPI_INFO_NULL, fileh, ierr )

  ! the header size is:
  !  1 field of 1 integer ( = 4*(1 + 1 + 1) = 12 bytes )
  ! +1 field of 5 integers( = 4*(1 + 5 + 1) = 28 bytes )
  ! +1 field of 7 integers( = 4*(1 + 7 + 1) = 36 bytes )
  ! +first bookend of array size = 4 bytes
  offset = 12 + 28 + 36 + 4

  ! rank 1 writes the header and footer
  if (rank == 0) then
      call MPI_File_write(fileh, [4, ngrid, 4], 3, MPI_INTEGER, &
                          MPI_STATUS_IGNORE, ierr)
      call MPI_File_write(fileh, [20, jd, kd, ld, nq, nqc, 20], 7, MPI_INTEGER, &
                          MPI_STATUS_IGNORE, ierr)
      call MPI_File_write(fileh, &
                        [28, refmach, alpha, rey, time, gaminf, beta, tinf, 28],&
                         9, MPI_INTEGER, MPI_STATUS_IGNORE, ierr)

      call MPI_File_write(fileh, [jd*kd*ld*nq*4], 1, MPI_INTEGER,  &
                         MPI_STATUS_IGNORE, ierr)
      call MPI_File_seek(fileh, offset+jd*kd*ld*nq*4, MPI_SEEK_CUR, ierr)
      call MPI_File_write(fileh, [jd*kd*ld*nq*4], 1, MPI_INTEGER,  &
                         MPI_STATUS_IGNORE, ierr)
  endif

  ! now everyone dumps their part of the array
  call MPI_File_set_view(fileh, offset, MPI_INTEGER, subarray,   &
                                'native', MPI_INFO_NULL, ierr)
  call MPI_File_write_all(fileh, q, jd*kd*ld*nlocq, MPI_INTEGER, &
                                MPI_STATUS_IGNORE, ierr)

  call MPI_File_close(fileh, ierr)

  CALL MPI_Finalize(ierr)

end program mpiwrite

在这个程序中,进程 0 负责写入表头和记录字段。它首先写入三个标头记录,每个记录以字节为单位的记录长度结束;然后它为大 Q 数组写入两个书挡。

然后,每个等级将文件视图设置为首先跳过标题,然后仅描述其全局数组的一部分(此处仅填充其等级编号),并写出其本地数据。这些都是不重叠的数据。

所以让我们用几个不同的尺寸来试试这个:

$ mpif90 -o mpifwrite mpifwrite.f90
$ mpirun -np 1 ./mpifwrite

$ ./fread mpi.dat
 Ngrid =            2
 jd, kd, ld, nq, nqc =            3           3           3           3          -1
 q: min/mean/max =            0           0           0

$ od --format="d" mpi.dat
0000000           4           2           4          20
0000020           3           3           3           3
0000040          -1          20          28           1
0000060           2           3           4           5
0000100           6           7          28         324
0000120           0           0           0           0
*
0000740           0         324
0000750

$ mpirun -np 3 ./mpifwrite
$ ./fread mpi.dat
 Ngrid =            2
 jd, kd, ld, nq, nqc =            3           3           3           9          -1
 q: min/mean/max =            0           1           2

$ od --format="d" mpi.dat
0000000           4           2           4          20
0000020           3           3           3           9
0000040          -1          20          28           1
0000060           2           3           4           5
0000100           6           7          28         972
0000120           0           0           0           0
*
0000620           0           1           1           1
0000640           1           1           1           1
*
0001320           1           1           2           2
0001340           2           2           2           2
*
0002020           2           2           2           0
0002040           0           0           0           0
*
0002140           0           0           0         972
0002160

这是我们期望的输出。将事物扩展到多种数据类型或多个网格相对简单。

于 2015-01-15T18:26:08.683 回答